Skip to main content
Glama
Sign In

Arrumou Neural

by io.github.brunoreisportela
OverviewDiscussionsAdmin

Preparar mensagem ao hóspede

draft_guest_message
Read-onlyIdempotent

Monta a mensagem final (variáveis preenchidas), o destinatário e o link wa.me. Nada é enviado nem registrado. Para check-in gera o link de check-in online.

Escopo: messages:draft · Risco: read · Efeitos: Pode gerar o token de check-in online da estadia. · INDISPONÍVEL nesta autorização (escopo não concedido ou papel sem o módulo)

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "reservation_id": "<reservation_id>"
    },
    "name": "draft_guest_message"
  }
}

Input Schema

NameRequiredDescriptionDefault
bodyNoTexto livre com variáveis; se omitido usa o modelo.
kindNoTEMPLATE
template_idNo
reservation_idYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

B3.4/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnly/idempotent/non-destructive, and the description adds two things they don't cover: that no message is sent or persisted, and that it may generate the stay's online check-in token. It also warns the tool is unavailable under the current authorization/scope, which is valuable pre-call context.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with the outcome (message + recipient + link) and constrained to a few short lines. The scope/risk/availability metadata line is dense but still earns its place as routing information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

No output schema exists, so the description must convey what comes back — it names the three returned artifacts (message, recipient, wa.me link) but not their shape. Combined with undocumented parameters and the unavailability note, it is adequate but leaves real gaps for a 4-parameter tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters2/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is only 25% (only `body` is documented), so the description needs to compensate but largely doesn't. It hints at check-in behavior that maps to `kind=CHECKIN`, but `template_id`, `reservation_id`, and the VOUCHER/TEMPLATE enum values get no explanation anywhere.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a concrete verb and outputs: assembles the final message with filled variables, the recipient, and a wa.me link. The 'Nada é enviado nem registrado' clause effectively separates it from send_guest_message, though that sibling is never named explicitly.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The 'nada é enviado nem registrado' line implies the draft/preview use case versus an actual send, and 'Para check-in gera o link de check-in online' gives a conditional behavior. However, no alternative is named and no explicit 'use this when / not when' routing is provided.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All Arrumou Neural toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources